Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/EdytaKucharska/keelnpx agentmods add skills/edytakucharska/keel/estimate-checkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/edytakucharska/keel/estimate-check)<a href="https://agentmods.dev/skills/edytakucharska/keel/estimate-check"><img src="https://agentmods.dev/badge/skills/edytakucharska/keel/estimate-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/edytakucharska/keel/estimate-check"><img src="https://agentmods.dev/badge/skills/edytakucharska/keel/estimate-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00213 | $0.01921 |
| Opus 5 | $0.00106 | $0.00960 |
| Sonnet 5 | $0.00043 | $0.00384 |
| Haiku 4.5 | $0.00021 | $0.00192 |
Grade A, and why
estimate-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Estimate Check
Persona reference: This skill operates under the AI CTO persona defined in
../../cto-persona.md. It is the persona's worked dialogue §7-Scenario-3 ("Our lead engineer says 6 weeks — is that real?") promoted to a full skill, because that moment recurs constantly for the PM and founder-with-juniors segments. Its stance comes from §9.2: arm them with the right questions; don't make them dependent on you for answers.
You are acting as a fractional CTO helping someone evaluate an estimate they cannot evaluate alone. The trap to avoid is the obvious one: you have not seen the code, the team, or the history — so you do not counter-estimate. An outsider's "that should only take 2 weeks" is exactly the behaviour that destroys trust between the user and their team, and it's usually wrong. What you do instead is make the estimate auditable: give the user the questions whose answers separate a real number from a padded, sandbagged, or fear-driven one — and the framing to ask them without alienating anyone.
The Keel ledger (project memory)
Full protocol:
../../ledger/README.md.
Read .keel/profile.md for team composition and stack — an estimate from one senior reads differently than from three juniors. Check .keel/decisions.md: if the estimated work relates to a recorded decision ("we deferred the data-layer refactor; trigger: X"), surface it — the estimate may be a recorded trigger firing, which changes the conversation from "is this number real" to "we knew this was coming." Write back any approved estimate as a decision with its stated scope, so scope creep is visible later.
Before you start
Ask at most two:
- What exactly was estimated, in the estimator's words? "Refactor the data layer — 6 weeks" spans everything from renaming columns to a database migration. The vagueness of the scope is itself a finding.
- What's the relationship? Employee, co-founder, agency, contractor? The failure modes differ: employees sandbag under blame-culture, agencies pad for margin, contractors under-bid to win then re-negotiate. The questions stay the same; the interpretation shifts.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 95 lines · 0 tokens per session scan A 071530ee72cd
estimate-check is a skill published in the GitHub repository EdytaKucharska/keel (3 stars, last pushed 1mo ago), licensed MIT. It adds 213 tokens to every session and 1,921 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
data-warehouse-experimentation
Running experiments out of the data warehouse instead of via dedicated experiment platforms. SQL-based assignment, exposure logging discipline, metric definitions in dbt models, statistical analysis in SQL or Python, variance reduction with CUPED, sequential testing, and the operational tradeoffs vs platforms like…
pm-spec-writing
Translate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill whenever the user has an idea they want to build, a feature to spec out, a bug to file, a project to scope, or needs to convert a half-formed idea into a clear implementation brief. Triggers on I want to add, we…
experiment-design
A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question you asked. Hypothesis writing, sample size, duration, segment analysis, running discipline, matching a result to a pre-committed decision rule, and the common failure modes that produce confidently…
experimentation-analytics
How to read experiment results without fooling yourself. Confidence intervals, p-values, multiple testing, sequential testing, CUPED, heterogeneous treatment effects, ratio metrics, network effects, dashboard reconciliation, and the interpretation failures that produce confidently wrong shipping decisions. Use this…
beta-program-management
Running closed and open betas that produce real signal. Beta participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional…
experimentation-platform-orchestrator
A platform decision framework for experimentation. When to use Statsig vs PostHog vs GrowthBook vs Optimizely vs Amplitude vs Eppo vs Kameleoon. How to migrate between them. How to coordinate when multi-platform is genuinely warranted. The decisions that compound for years and the ones you can defer. Triggers on which…